from DSSResources.com


What is surveillance analytics?

Ciara Heavin
and Daniel J. Power

Monitoring and tracking of people and our activities is not a new phenomenon. People have spied upon and kept track of the activities of others since the beginnings of recorded history. The tools and techniques have however gotten increasingly sophisticated. For example, individuals, police departments, and businesses have been implementing video-enabled security systems in homes, on the street, and on business premises as security measures. The amount of data captured has grown exponentially and analyzing data is increasingly challenging. Streaming, real-time data is increasingly monitored by software. Surveillance analytics involves the use of software algorithms to detect, classify, monitor, and track objects or persons in real-time or after an event, cf., Zalud, 2013.

Heibutzki (2018) defines surveillance narrowly as "the covert observation of people, places and vehicles, which law enforcement agencies and private detectives use to investigate allegations of illegal behavior. These techniques range from physical observation to the electronic monitoring of conversations." Surveillance equipment includes various gadget and devices including audio recorders, digital cameras, GPS tracking devices, real-time listening devices, night vision equipment, heat sensors, and traffic counters. Software may be used to intercept Internet traffic or keystrokes.

Surveillance and privacy concerns have become more important as advanced tools and technologies such as machine learning (ML), other AI technologies, and statistical predictive models are using data from closed circuit television (CCTV) cameras and other data sources to analyze human behavior in real-time (Japkowicz and Stefanowski, 2016). These emerging tools may be used to derive new insights to predict what may occur in the future. Surveillance analytics are used to identify a threat or incident and to understand a new market sector or opportunity.

Surveillance systems monitor behavior, activities, or other changing things to manage, direct, or protect people. AI including video analytics use large amounts of data generated by Internet of Things (IoT) surveillance systems to identify meaningful patterns in datasets. Also, often data is transformed into insights that can be used by security staff to develop preventative strategies. According to Bonoan and Ataev (2020), surveillance analytics may also be used to generate new insights about employee behavior and movement, as well as customer behavior including customer flow and dwelling time, hotspots, and product display activity.

Surveillance may also involve intercepting private emails or phone calls, passive or active video camera data collection and analysis, click-stream data from social media, monitoring Internet usage, and human intelligence gathering. Surveillance analytics is needed because people cannot interpret and monitor the vast amounts of surveillance data unaided. Advanced video analytics and facial recognition software are used extensively in real-time surveillance.

One example of surveillance analytics is the Electronic Surveillance System for the Early Notification of Community-based Epidemics (ESSENCE). A brief article at Health.Mil explains that ESSENCE is "a data mart within Department of Health and Human Services’ Executive Information/Decision Support (EI/DS) family of systems that uses outpatient information to monitor trends and increases in activity that may represent a disease outbreak, CBRN event, or significant other medical event. ESSENCE monitors and scans certain MHS clinical data sources continuously. When ESSENCE detects a potential event of Military Health Systems (MHS) interest the application provides an alert to users who are responsible for public health responses for that area or facility."

China's Golden Shield Project (Klein, 2008; Rajeck, 2017; Wikipedia), aka National Public Security Work Informational Project, is another example of an integrated surveillance analytics system. The Chinese government has installed millions of surveillance cameras throughout the country. The network of cameras, along with advanced video analytics and facial recognition software, helps identify and track individuals wherever they go. The project includes a security management information system, a criminal information system, an exit and entry administration information system, a supervisor information system, a traffic management information system, among others. When completed, the systems will be connected to a centralized database and monitoring station that will contain a digital image of the face of every person in China, over 1.3 billion people."

Decision support algorithms are creating new opportunities for automated detection and monitoring through the use of surveillance devices (Power, 2014; 2016). For Artificial Intelligence (AI) driven surveillance systems to be truly effective, edge to cloud storage infrastructure must become more mainstream. To accommodate such big data in the form of video data and metadata from the surveillance analytics, a new architecture using both edge and cloud computing is needed (Bonoan and Ataev, 2020).

Surveillance analytics uses machine learning, quantitative and statistical analysis of data to monitor and predict behavior, detect problems, take proactive actions, and identify things, including people, license plate numbers, and locations. Surveillance analytics can trigger routine actions or support more complex, non-routine decision-making.

References

Bonoan, J and Atave, A. (2020). "AI and Specialty Analytics are Changing Video Surveillance, https://www.securityinfowatch.com/video-surveillance/article/21125810/ai-and-specialty-analytics-are-changing-video-surveillance

Health.mil, "Electronic Surveillance System for the Early Notification of Community-based Epidemics," at URL https://www.health.mil/Military-Health-Topics/Combat-Support/Armed-Forces-Health-Surveillance-Branch/Integrated-Biosurveillance/ESSENCE

Heibutzki, R., "Types of Surveillance in Criminal Investigations," Chron, updated July 01, 2018 at URL https://work.chron.com/types-surveillance-criminal-investigations-9434.html

Japkowicz, N. and J. Stefanowski. (2016). A Machine Learning Perspective on Big Data Analysis. In: Japkowicz N., Stefanowski J. (eds) Big Data Analysis: New Algorithms for a New Society. Studies in Big Data, vol 16. Springer, Cham.

Klein, Naomi (May 29, 2008). "China's All-Seeing Eye". Rolling Stone at URL https://web.archive.org/web/20090326152758/http://www.rollingstone.com/politics/story/20797485/chinas_allseeing_eye/print

Power, D. J. (2016). “Big Brother” can watch us, Journal of Decision Systems, Volume 25, 2016 - Issue sup1, 578-588 https://doi.org/10.1080/12460125.2016.1187420

Power, D. J. (2014). Using ‘Big Data’ for analytics and decision support, Journal of Decision Systems, 23: 222-228 https://doi.org/10.1080/12460125.2014.888848 .

Rajeck, J.(2017). "The Great Firewall of China 2017 update: The good and the bad," econsultancy, April 2 at URL https://econsultancy.com/the-great-firewall-of-china-2017-update-the-good-and-the-bad/

Wikipedia, "Golden Shield Project" from Wikipedia, the free encyclopedia at URL https://en.wikipedia.org/wiki/Golden_Shield_Project

Zalud, B. (2013). 9 Ongoing Trends for Surveillance Analytics, Retrieved from https://www.securitymagazine.com/articles/83984-ongoing-trends-for-surveillance-analytics.

Last update: 2020-09-13 12:29
Author: Daniel Power

Print this record Print this record
Show this as PDF file Show this as PDF file

Please rate this entry:

Average rating: 5 from 5 (2 Votes )

completely useless 1 2 3 4 5 most valuable

You cannot comment on this entry





DSS Home |  About Us |  Contact Us |  Site Index |  Subscribe | What's New
Please Tell Your Friends about DSSResources.COMCopyright © 1995-2015 by D. J. Power (see his home page).
DSSResources.COMsm is maintained by Daniel J. Power. Please contact him at djpower1950@gmail.com with questions. See disclaimer and privacy statement.


Google
 
Web DSSResources.com

powered by phpMyFAQ 1.5.3